Apparatus, system, and method for scanning segmentation
OwnerJoseph Stanley Czyszczewski, Hong Li +1inventors
InventorsJoseph Stanley Czyszczewski, Hong Li, James T. Smith, II
Life of this patent
Estimating the term…
Abstract
An apparatus, system, and method are disclosed for identifying content within a scanned document. The apparatus includes a modification module, an identification module, and a segmentation module. The modification module creates a modified content data set through application of a sigmoid function to a scanned content data set. The identification module identifies a content segment within the modified content data set. The segmentation module identifies a content segment type of the content segment. Exemplary content segment types include text, line art, and images.
Claims18
A system configured to identify content within a scanned image, the system comprising:
- a scanner configured to capture a scanned content data set;
- an electronic storage coupled with the scanner and configured to store the scanned content data set;
- and
- a segmentation apparatus coupled with the electronic storage and configured to create a modified content data set through application of a sigmoid function to the scanned content data set, to identify a content segment within the modified content data set by determining eight neighbor connectedness with a substantially black pixel to identify the pixels within the content segment, to identify a content segment type of the content segment, to calculate a segment surface area of the content segment within the modified content data set, and to compare the segment surface area to a minimum image surface area.
A system configured to identify content within a scanned image, the system comprising:
- a scanner configured to capture and digitize scanned content having a content segment;
- an electronic data storage device configured to store a scanned content data set descriptive of the digitized scanned content;
- and
- a segmentation apparatus configured to identify a content segment type of the content segment, and further configured to create a modified content data set from the scanned content data set, the modified content data set corresponding to a modified content histogram that is more polarized than a scanned content histogram corresponding to the scanned content data set and wherein the modified content data set relates to the scanned content data set according to a sigmoid function substantially similar to the following:
- f
-
- (
- x
- )
- =
- (
- x
- 128
- )
- n
- ×
- 128
- 0
- <
- x
- <
- 128
- f
-
- (
- x
- )
- =
- 255
- -
- (
- 255
- -
- x
- 127
- )
- n
- ×
- 127
- 128
- <
- x
- <
- 255
- in which n is a parameter that determines the shape of the sigmoid function, x is a pixel value of a pixel of the scanned content data set, and f(x) defines a corresponding modified pixel value of a modified pixel of the modified content data set.
A computer readable medium tangibly embodying programmed instructions which, when executed by a computer system, are operable for performing a method of identifying content within a scanned image, the method comprising:
- creating a modified content data set through application of a sigmoid function to a scanned content data set;
- identifying a content segment within the modified content data set by determining eight neighbor connectedness with a substantially black pixel to identify the pixels within the content segment;
- identifying a content segment type of the content segment;
- calculating a segment surface area of a content segment within the modified content data set;
- and
- comparing the segment surface area to a minimum image surface area.
A computer implemented method of identifying content within a scanned image, the method comprising:
- creating a modified content data set using a computer through application of a sigmoid function to a scanned content data set;
- identifying a content segment within the modified content data set using the computer by determining eight neighbor connectedness with a substantially black pixel to identify the pixels within the content segment;
- identifying a content segment type of the content segment using the computer;
- calculating a segment surface area of a content segment within the modified content data set using the computer;
- and
- comparing the segment surface area to a minimum image surface area using the computer.
Dependencies are inferred from the claim text.